👋 About me

I am a Researcher at WeChat AI, Tencent, where I conduct research on multi-modal learning. I joined through the Qingyun Program (青云计划, formerly the Technology Daka Program / 技术大咖), Tencent’s top-tier talent program for outstanding technical graduates. Prior to WeChat AI, I was a research intern with the 3D Vision Group at SenseTime Singapore.

I received my Ph.D. from the School of Software Engineering at South China University of Technology (SCUT) and Nanyang Technological University (NTU), advised by Prof. Qingyao Wu and Prof. Guosheng Lin. I also work closely with Dr. Fengyun Rao in research.

✏️ Research Interests

• Fundamental Vision: Detection, Segmentation, and Restoration
• Multi-Modal Learning: Variant CLIP and Multimodal Large Language Models (MLLMs)
• AIGC: Text-2-Video Generation and Video Editing

📰 News

• 2026.05: One paper is accepted by ICML 2026 !
• 2026.04: One paper is accepted by Expert Systems with Applications 2026 !
• 2026.01: One paper is accepted by CVPR 2026 !
• 2024.08: One paper is accepted by Pattern Recognition (PR) 2024 !
• 2023.12: One paper is accepted by AAAI 2024 !
• 2023.06: One paper is accepted by Pattern Recognition (PR) 2023 !
• 2023.04: One paper is accepted by Transactions On MultiMedia (TMM) 2023 and the code and demo are released!
• 2023.03: One paper is accepted by AAAI 2023 and is selected as Oral !
• 2022.08: Two papers are accepted by AAAI 2022 and ECCV 2022 !
• 2021.08: Three papers are accepted by ICCV 2021 and ACM MM 2021 !
• 2020.08: One paper is accepted by ECCV 2020 and is selected as Spotlight !